8 papers
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
Yanis Labrak, Dairazalia Sanchez-Cortes, Sergio Burdisso +9
In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is a…
SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification
Junyi Peng, OldÅich Plchot, Xiao Song +9
Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora ta…
FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
Santosh Kesiraju, Bolaji Yusuf, Å imon SedláÄek +2
This paper presents factorized linear projection (FLiP) models for understanding pretrained sentence embedding spaces. We train FLiP models to recover the lexical content from mult…
State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
Sara Barahona, Ladislav Mošner, Themos Stafylakis +4
In this paper, we refine and validate our method for training speaker embedding extractors using weak annotations. More specifically, we use only the audio stream of the source Vox…
Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing
Junyi Peng, Lin Zhang, Jiangyu Han +5
Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on…
Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
Pradyoth Hegde, Santosh Kesiraju, Jan Å vec +5
This study explores the application of in-context learning (ICL) to the dialogue state tracking (DST) problem and investigates the factors that influence its effectiveness. We use…